[Feature]: Add support for the Bedrock Embeddings Model `amazon.titan-embed-g1-text-02`

[mirodrr2]

The Feature

import openai
import os
from dotenv import load_dotenv

load_dotenv()

api_key=os.getenv("LITELLM_PROXY_API_KEY"),
api_base=os.getenv("LITELLM_PROXY_API_BASE"),

client = openai.OpenAI(
    api_key=api_key,
    base_url=api_base
)

model_id = "amazon.titan-embed-g1-text-02"
response = client.embeddings.create(model=model_id, input="What is this")
print(len(response.data[0].embedding))

openai.InternalServerError: Error code: 500 - {'error': {'message': 'litellm.APIConnectionError: Unable to map Bedrock request to provider\nTraceback (most recent call last):\n  File "/usr/lib/python3.13/site-packages/litellm/main.py", line 3566, in embedding\n    response = bedrock_embedding.embeddings(\n        model=model,\n    ...<11 lines>...\n        extra_headers=extra_headers,\n    )\n  File "/usr/lib/python3.13/site-packages/litellm/llms/bedrock/embed/embedding.py", line 448, in embeddings\n    raise Exception("Unable to map Bedrock request to provider")\nException: Unable to map Bedrock request to provider\n. Received Model Group=amazon.titan-embed-g1-text-02\nAvailable Model Group Fallbacks=None', 'type': None, 'param': None, 'code': '500'}}

Motivation, pitch

This is still a relevant model for bedrock, and has not been deprecated yet

Are you a ML Ops Team?

No

Twitter / LinkedIn details

No response

[cclawton]

Very important feature for my usecase

[cclawton]

Very important feature for my usecase

[github-actions]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs.

[twinity1]

++